Codes for our paper "Programming Biomolecular Interactions with All-Atom Generative Model"

Code for running RFdiffusion

[NeurIPS2025 Spotlight 🔥 ] Official implementation of "UniSite: The First Cross-Structure Dataset and Learning Framework for End-to-End Ligand Binding Site Detection"

Toward High-Accuracy Open-Source Biomolecular Structure Prediction.

A Euclidean diffusion model for structure-based drug design.

MaSIF- Molecular surface interaction fingerprints. Geometric deep learning to decipher patterns in molecular surfaces.

Knowledge-Guided Diffusion Model for 3D Ligand-Pharmacophore Mapping

Official Github for "PharmacoNet: deep learning-guided pharmacophore modeling for ultra-large-scale virtual screening" (Chemical Science)

Extensible Surrogate Potential of Ab initio Learned and Optimized by Message-passing Algorithm 🍹https://arxiv.org/abs/2010.01196

End-To-End Molecular Dynamics (MD) Engine using PyTorch

IF-SitePred is a method for predicting ligand-binding sites on protein structures. It first generates an embedding for each residue of the protein using the ESM-IF1 (inverse folding) model, then performs point cloud clustering to identify binding site centers.

Prediction of binding residues for metal ions, nucleic acids, and small molecules.

NequIP is a code for building E(3)-equivariant interatomic potentials

Predicting protein-ligand binding sites using deep convolutional neural network

EquiBind: geometric deep learning for fast predictions of the 3D structure in which a small molecule binds to a protein

This package contains deep learning models and related scripts for RoseTTAFold

Training and inference code for ShEPhERD: Diffusing shape, electrostatics, and pharmacophores for bioisosteric drug design [ICLR 2025 oral]

RXNMapper: Unsupervised attention-guided atom-mapping. Code complementing our Science Advances publication on "Extraction of organic chemistry grammar from unsupervised learning of chemical reactions" (https://advances.sciencemag.org/content/7/15/eabe4166).